CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : speed up tests (#15836)

Browse Source 
* server : speed up tests

* clean up

* restore timeout_seconds in some places

* flake8

* explicit offline
This commit is contained in:
Xuan-Son Nguyen
2025-09-06 19:45:24 +07:00
committed by GitHub
parent 61bdfd5298
commit 3c3635d2f2
6 changed files with 90 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tools/server/tests/unit/test_template.py
View File

@@ -14,14 +14,11 @@ from utils import *
server: ServerProcess
TIMEOUT_SERVER_START = 15*60
@pytest.fixture(autouse=True)
def create_server():
global server
server = ServerPreset.tinyllama2()
server.model_alias = "tinyllama-2"
server.server_port = 8081
server.n_slots = 1
@@ -45,7 +42,7 @@ def test_reasoning_budget(template_name: str, reasoning_budget: int | None, expe
server.jinja = True
server.reasoning_budget = reasoning_budget
server.chat_template_file = f'../../../models/templates/{template_name}.jinja'
server.start(timeout_seconds=TIMEOUT_SERVER_START)
server.start()
res = server.make_request("POST", "/apply-template", data={
"messages": [
@@ -68,7 +65,7 @@ def test_date_inside_prompt(template_name: str, format: str, tools: list[dict]):
global server
server.jinja = True
server.chat_template_file = f'../../../models/templates/{template_name}.jinja'
server.start(timeout_seconds=TIMEOUT_SERVER_START)
server.start()
res = server.make_request("POST", "/apply-template", data={
"messages": [
@@ -91,7 +88,7 @@ def test_add_generation_prompt(template_name: str, expected_generation_prompt: s
global server
server.jinja = True
server.chat_template_file = f'../../../models/templates/{template_name}.jinja'
server.start(timeout_seconds=TIMEOUT_SERVER_START)
server.start()
res = server.make_request("POST", "/apply-template", data={
"messages": [